© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81261
    Prev
    Next
    INDEX
    Explanations

    angular framework

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “Angular,” marking mentions of the Angular framework.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Istanbul
    -0.86
     bonté
    -0.82
     Hillsborough
    -0.81
    加载
    -0.81
    Himal
    -0.79
     trabalhos
    -0.79
     Allegheny
    -0.78
     番目
    -0.78
    BRAS
    -0.77
     Игорь
    -0.77
    POSITIVE LOGITS
    ULAR
    0.90
     momentum
    0.85
     displacement
    0.85
    ities
    0.84
    ity
    0.84
     Harp
    0.82
     distribution
    0.79
     nahezu
    0.77
     frequency
    0.77
     folgte
    0.75
    Activations Density 0.021%

    No Known Activations